Highlights
- Pro
Stars
A local-first retrieval engine that turns notes, docs, and code into a searchable knowledge base for humans and AI agents.
Upstream-based Ghostty repository for embeddable tmux control mode and Remux integration
Practical marketing resources to get the first 10 / 100 / 1000 users for your SaaS / App / Startup
A native iOS client for remote tmux workspaces, designed to feel natural on iPhone.
Control panel for VLLM, Sglang, llama.cpp, exllamav3
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
The fastest and the most accurate file search SDK for AI agents, Neovim, Rust, C, Python, Bun and NodeJS
An open source, self-hosted implementation of the Tailscale control server
A fast TUI dashboard for Codex quota, cost, and token activity
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
Lightweight and Memory efficient terminal for Mac built with SwiftUI and libghostty
Robust Speech Recognition via Large-Scale Weak Supervision
Crabbox: warm a box, sync the diff, run the suite.
Show usage stats for OpenAI Codex and Claude Code, without having to login.
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
Warp is an agentic development environment, born out of the terminal.
AI that sees your screen, listens to your conversations and tells you what to do
A machine learning library with a TypeScript API and Rust backend. CUDA and WebGPU compatibility. Built to understand how ML frameworks and models work internally.
Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
A minimum viable terminal emulator built on top of the libghostty C API. Ex minimo, infinita nascuntur. 👻🐣
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Train the smallest LM you can that fits in 16MB. Best model wins!